utils/pdf_utils.py

import os
from pathlib import Path

from PyPDF2 import PdfReader


def extract_text_from_pdf(pdf_path: str) -> str:
    """
    Extract all text from a PDF file.

    Args:
        pdf_path: Path to the PDF file

    Returns:
        Extracted text as a single string
    """
    if not os.path.exists(pdf_path):
        raise FileNotFoundError(f"PDF not found: {pdf_path}")

    text = []
    try:
        with open(pdf_path, "rb") as file:
            pdf_reader = PdfReader(file)
            for page in pdf_reader.pages:
                text.append(page.extract_text())
    except Exception as e:
        raise ValueError(f"Error reading PDF {pdf_path}: {e}")

    return "\n".join(text)


def list_papers(papers_dir: str = "papers") -> list:
    """
    List all PDF files in the papers directory.

    Args:
        papers_dir: Directory containing test papers

    Returns:
        List of absolute paths to PDF files
    """
    papers_path = Path(papers_dir)
    if not papers_path.exists():
        return []

    return [str(f) for f in papers_path.glob("*.pdf") if f.is_file()]